Merge pull request #3699 from Cheukting/py311_regex

hypothesis-python/RELEASE.rst

@@ -0,0 +1,7 @@
+RELEASE_TYPE: minor
+
+:func:`~hypothesis.strategies.from_regex` now supports the atomic grouping
+(``(?>...)``) and possessive quantifier (``*+``, ``++``, ``?+``, ``{m,n}+``)
+syntax `added in Python 3.11 <https://docs.python.org/3/whatsnew/3.11.html#re>`__.
+
+Thanks to Cheuk Ting Ho for implementing this!

hypothesis-python/src/hypothesis/strategies/_internal/regex.py

@@ -14,10 +14,16 @@
 try:  # pragma: no cover
     import re._constants as sre
     import re._parser as sre_parse
+
+    ATOMIC_GROUP = sre.ATOMIC_GROUP
+    POSSESSIVE_REPEAT = sre.POSSESSIVE_REPEAT
 except ImportError:  # Python < 3.11
     import sre_constants as sre
     import sre_parse
 
+    ATOMIC_GROUP = object()
+    POSSESSIVE_REPEAT = object()
+
 from hypothesis import reject, strategies as st
 from hypothesis.internal.charmap import as_general_categories, categories
 from hypothesis.internal.compat import int_to_byte
@@ -474,7 +480,7 @@ def recurse(codes):
             # Regex 'a|b|c' (branch)
             return st.one_of([recurse(branch) for branch in value[1]])
 
-        elif code in [sre.MIN_REPEAT, sre.MAX_REPEAT]:
+        elif code in [sre.MIN_REPEAT, sre.MAX_REPEAT, POSSESSIVE_REPEAT]:
             # Regexes 'a?', 'a*', 'a+' and their non-greedy variants
             # (repeaters)
             at_least, at_most, subregex = value
@@ -494,8 +500,12 @@ def recurse(codes):
                 recurse(value[1]),
                 recurse(value[2]) if value[2] else st.just(empty),
             )
+        elif code == ATOMIC_GROUP:  # pragma: no cover  # new in Python 3.11
+            return _strategy(value, context, is_unicode)
 
         else:
             # Currently there are no known code points other than handled here.
             # This code is just future proofing
-            raise NotImplementedError(f"Unknown code point: {code!r}")
+            raise NotImplementedError(
+                f"Unknown code point: {code!r}.  Please open an issue."
+            )

hypothesis-python/tests/nocover/test_regex.py

@@ -10,8 +10,11 @@
 
 import re
 import string
+import sys
 from functools import reduce
 
+import pytest
+
 from hypothesis import assume, given, reject, strategies as st
 from hypothesis.strategies._internal.regex import base_regex_strategy
 
@@ -86,6 +89,22 @@ def test_fuzz_stuff(data):
     assert regex.search(ex)
 
 
+@pytest.mark.skipif(sys.version_info[:2] < (3, 11), reason="new syntax")
+@given(st.data())
+def test_regex_atomic_group(data):
+    pattern = "a(?>bc|b)c"
+    ex = data.draw(st.from_regex(pattern))
+    assert re.search(pattern, ex)
+
+
+@pytest.mark.skipif(sys.version_info[:2] < (3, 11), reason="new syntax")
+@given(st.data())
+def test_regex_possessive(data):
+    pattern = '"[^"]*+"'
+    ex = data.draw(st.from_regex(pattern))
+    assert re.search(pattern, ex)
+
+
 # Some preliminaries, to establish what's happening:
 I_WITH_DOT = "\u0130"
 assert I_WITH_DOT.swapcase() == "i\u0307"  # note: string of length two!